Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    может, cannot, не

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.33
     innymi
    0.31
     samoglas
    0.29
    단의
    0.28
     radiometric
    0.28
    ။
    0.28
    larım
    0.27
    듦
    0.27
     რამდ
    0.27
     kerusakan
    0.27
    POSITIVE LOGITS
     не
    0.44
     може
    0.38
     может
    0.37
     had
    0.37
     could
    0.36
     नहीं
    0.36
     může
    0.34
     buvo
    0.34
     δεν
    0.33
    ไม่
    0.33
    Act Density 0.082%

    No Known Activations